Filters








2 Hits in 3.7 sec

ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models [article]

Yugeng Liu and Rui Wen and Xinlei He and Ahmed Salem and Zhikun Zhang and Michael Backes and Emiliano De Cristofaro and Mario Fritz and Yang Zhang
2021 arXiv   pre-print
In this paper, we fill this gap by presenting a first-of-its-kind holistic risk assessment of different inference attacks against machine learning models.  ...  Inference attacks against Machine Learning (ML) models allow adversaries to learn sensitive information about training data, model parameters, etc.  ...  Experimental Evaluation In this section, we build on ML-DOCTOR to provide a holistic assessment of inference attacks against ML models.  ... 
arXiv:2102.02551v2 fatcat:b4mlkrmst5fotgssos7u4dbohy

SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning [article]

Vasisht Duddu, Sebastian Szyller, N. Asokan
2021 arXiv   pre-print
Data used to train machine learning (ML) models can be sensitive.  ...  Membership inference attacks (MIAs), attempting to determine whether a particular data record was used to train an ML model, risk violating membership privacy.  ...  Ml-doctor: Holistic risk assessment of inference attacks cessed: 2021-11-27. against machine learning models.  ... 
arXiv:2112.02230v1 fatcat:zc4vslnrejecxdcpnebn3lally